{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39927613", "kind": "science-record", "revision": 2, "content_hash": "sha256:7b6519f5e490e770da41b1ed4b4cf443ffb0ad31f2cd5d79f98c6d7029524916", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T14:01:34Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Classification of acute myeloid leukemia based on multi-omics and prognosis prediction value.", "doi": "10.1002/1878-0261.70000", "pmid": "39927613", "authors": null, "journal": "Molecular oncology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:39927613"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:39927613", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:39927613' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39927613", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/1878-0261.70000", "sha256": "sha256:0eff4cb0fc86ed00876123c89113527f0e388d7836da336fb847769bddf79f53", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/1878-0261.70000", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:39927613:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a1b96df705412438896cfdc5bac41854dbba1220dece52a76832689f198c989e", "bytes": 2515, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#mol270000-tbl-0001", "version": null, "note": "Clinical characteristics in ihCAMs‐AML cohort (N = 98) under UAMOCS. ELN, European LeukemiaNet; HSCT, hematopoietic stem cell transplantation; ND, newly diagnosed; R/R, relapsed/refractory.", "structure": {"pmcid": "PMC12161470", "section_index": 6, "section_title": "Participants of ihCAMs‐AML cohort for validation", "row_count": 29, "column_count": 10}, "table": {"label": "Table 1", "caption": "Clinical characteristics in ihCAMs‐AML cohort (N = 98) under UAMOCS. ELN, European LeukemiaNet; HSCT, hematopoietic stem cell transplantation; ND, newly diagnosed; R/R, relapsed/refractory.", "rows": [["", "Level", "Overall", "UAMOCS1", "UAMOCS2", "UAMOCS3", "Overall P", "UAMOCS1 vs. UAMOCS2 P‐value", "UAMOCS1 vs. UAMOCS3 P‐value", "UAMOCS2 vs. UAMOCS3 P‐value"], ["N", "", "98", "23", "38", "37", "", "", "", ""], ["Disease status (%)", "ND", "80 (81.6)", "18 (78.3)", "30 (78.9)", "32 (86.5)", "0.625", "1.000", "0.635", "0.577"], ["R/R", "18 (18.4)", "5 (21.7)", "8 (21.1)", "5 (13.5)"], ["Age (%)", "≤ 55", "80 (81.6)", "15 (65.2)", "32 (84.2)", "33 (89.2)", "0.058", "0.163", "0.054", "0.768"], ["> 55", "18 (18.4)", "8 (34.8)", "6 (15.8)", "4 (10.8)"], ["Sex (%)", "Female", "47 (48.0)", "9 (39.1)", "18 (47.4)", "20 (54.1)", "0.529", "0.717", "0.390", "0.728"], ["Male", "51 (52.0)", "14 (60.9)", "20 (52.6)", "17 (45.9)"], ["HSCT (%)", "No", "74 (75.5)", "19 (82.6)", "28 (73.7)", "27 (73.0)", "0.662", "0.625", "0.586", "1.000"], ["Yes", "24 (24.5)", "4 (17.4)", "10 (26.3)", "10 (27.0)"], ["Status (%)", "Alive", "62 (63.3)", "8 (34.8)", "23 (60.5)", "31 (83.8)", "0.001", "0.092", "< 0.001", "0.047"], ["Dead", "36 (36.7)", "15 (65.2)", "15 (39.5)", "6 (16.2)"], ["FAB classification (%)", "M0", "1 (1.0)", "1 (4.3)", "0 (0.0)", "0 (0.0)", "0.001", "0.169", "0.107", "< 0.001"], ["M1", "4 (4.1)", "1 (4.3)", "1 (2.6)", "2 (5.4)"], ["M2", "35 (35.7)", "8 (34.8)", "5 (13.2)", "22 (59.5)"], ["M4", "18 (18.4)", "3 (13.0)", "8 (21.1)", "7 (18.9)"], ["M5", "40 (40.8)", "10 (43.5)", "24 (63.2)", "6 (16.2)"], ["Cytogenetic group (%)", "Adverse", "18 (18.4)", "8 (34.8)", "8 (21.1)", "2 (5.4)", "0.044", "0.244", "0.007", "0.136"], ["Favorable", "21 (21.4)", "2 (8.7)", "9 (23.7)", "10 (27.0)"], ["Normal", "59 (60.2)", "13 (56.5)", "21 (55.3)", "25 (67.6)"], ["Cytogenetic abnormality (%)", "Complex", "7 (7.1)", "4 (17.4)", "1 (2.6)", "2 (5.4)", "0.002", "0.162", "0.031", "0.002"], ["del(7)", "1 (1.0)", "1 (4.3)", "0 (0.0)", "0 (0.0)"], ["inv(16)", "9 (9.2)", "1 (4.3)", "7 (18.4)", "1 (2.7)"], ["MLL rearrangement", "10 (10.2)", "3 (13.0)", "7 (18.4)", "0 (0.0)"], ["None", "59 (60.2)", "13 (56.5)", "21 (55.3)", "25 (67.6)"], ["t(8;21)", "12 (12.2)", "1 (4.3)", "2 (5.3)", "9 (24.3)"], ["2022 ELN (%)", "Adverse", "33 (33.7)", "15 (65.2)", "14 (36.8)", "4 (10.8)", "0.001", "0.097", "< 0.001", "0.023"], ["Favorable", "46 (46.9)", "5 (21.7)", "16 (42.1)", "25 (67.6)"], ["Intermediate", "19 (19.4)", "3 (13.0)", "8 (21.1)", "8 (21.6)"]], "row_count": 29, "column_count": 10, "numeric_cells": 154, "header_rows": 1, "locator": "section[6]/table-wrap[1]#mol270000-tbl-0001"}}], "gaps": ["asset:source:pmid:39927613 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:39927613", "asset:table:pmid:39927613:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39927613"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "815a13ee8c081312b2e18c1226014c3661ccfed61e0822b801012fb6ef89ce57", "source_hash": "0eff4cb0fc86ed00876123c89113527f0e388d7836da336fb847769bddf79f53", "raw_response_sha256": "sha256:7d1bef25a3a3f10258d58db5b396865f357124a41726405a1384d2bae2e98a4a", "raw_response_chars": 7096}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "5a344647000d32ae81fbeef0cb2a24fdfbe4699143f2b4d810cc678bdced30a0", "source_hash": "0eff4cb0fc86ed00876123c89113527f0e388d7836da336fb847769bddf79f53", "raw_response_sha256": "sha256:b9daa3a0d00b47f0112c6b49cd337b54b38d02893b7caf3d2db6186c5f199f86", "raw_response_chars": 67460}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "6277f01bcc04cff46f90fb98e73cf992fb1f821ade42f412ebdc76cf7fd664d4", "source_hash": "0eff4cb0fc86ed00876123c89113527f0e388d7836da336fb847769bddf79f53", "raw_response": "{\"parent_value\":0.87,\"unit\":\"C-statistic\",\"evidence\":\"The model's C‐statistic is comparable to the 2022 ELN risk classification (0.87 vs 0.82; P = 0.162), but offers a more nuanced distinction between intermediate‐ and high‐risk groups.\",\"target_result\":\"The model reported a C-statistic of 0.87.\",\"number_stated\":true}", "reading": {"parent_value": 0.87, "unit": "C-statistic", "evidence": "The model's C‐statistic is comparable to the 2022 ELN risk classification (0.87 vs 0.82; P = 0.162), but offers a more nuanced distinction between intermediate‐ and high‐risk groups.", "target_result": "The model reported a C-statistic of 0.87.", "number_stated": true, "source_locator": "chars 1210-1392 of source sha256 0eff4cb0fc86ed00876123c89113527f0e388d7836da336fb847769bddf79f53"}, "recorded_at": "2026-10-31T15:23:58.237938+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "5a8f81af0c7b7655431929265bec7a75261601e102b12e1ff8edf2651f61e31e", "source_hash": "0eff4cb0fc86ed00876123c89113527f0e388d7836da336fb847769bddf79f53", "raw_response": "<think>We need answer JSON only. Need identify single numerical result headline main finding stated. Source abstract. Registered target: headline numerical result paper states for main finding. Likely C-statistic 0.87 vs 0.82? Need infer \"headline number\" singular. The paper main finding multi-omics classification. Abstract numerical results include 1391 subjects, 3 cohorts, survival P values, C-statistic comparable 0.87 vs 0.82. They ask value paper itself states for registered target, not calculated. Which is headline numerical result? Perhaps target intended generic extraction benchmark where need identify main result from abstract, likely C-statistic 0.87. Need report headline number only, with exact contiguous quote containing number, attribution. Unit must paper prints. C-statistic dimensionless; unit perhaps empty? Could say \"C-statistic\" as unit? Schema parent_value numerical. They explicitly headline number only and unit printed. Evidence exact clause. Maybe number 1391? Main numerical result likely cohort size, but \"headline numerical result\" perhaps performance metric C-statistic 0.87 vs 0.82. Need parse wording: \"single numerical result that a replication of the registered target has to reproduce. REGISTERED TARGET: the headline numerical result the paper states for its main finding\". They expect one. Abstract ends: \"The model's C-statistic is comparable to the 2022 ELN risk classification (0.87 vs 0.82; P = 0.162), but offers...\" This is clearly a headline numerical performance result. But there are two numbers, own model vs comparator. \"value the paper itself states for registered target\" Target is main finding, likely headline numerical result = C-statistic 0.87. Need unit likely \"C-statistic\" or perhaps no unit. Evidence should exact contiguous quote and enough attribution. Quote whole clause: \"The model's C‐statistic is comparable to the 2022 ELN risk classification (0.87 vs 0.82; P = 0.162), but offers a more nuanced distinction between intermediate‐ and high‐risk groups.\" This identifies first 0.87 as model? Wording \"model's C-statistic ... (0.87 vs 0.82)\" implies yes, model vs ELN. Need quote exact typography. parent_value 0.87. unit perhaps \"C-statistic\". The instruction \"unit must be the unit the paper prints.\" It prints \"C-statistic\", but that's a metric, not unit. Could unit be empty string because dimensionless. They require unit string, empty allowed. They say leave unit and evidence empty only if no number. For stated, likely unit should reflect metric/unit. In common extraction tasks, unit maybe \"C-statistic\" or \"\" if dimensionless. \"Report the headline number only: the value...\" They might expect unit as \"C-statistic\" perhaps. target_result can state concise result. JSON only.\n\nCould there be a headline number of 1391 consecutive newly diagnosed subjects. A replication of main finding might need reproduce? Registered target phrased broad. Need understand likely dataset/question generation. It may be asking to identify numerical result from paper abstract. Headline numerical result usually abstract's quantitative performance. Here C-statistic 0.87 vs 0.82 is central. \"single numerical result\" means perhaps select 0.87. The evidence should include exact contiguous quote. Could include only sentence, no issue. target_result perhaps \"The model's C-statistic is 0.87, comparable to 0.82 for 2022 ELN.\" But they asked report headline number only—probably target_result perhaps explanatory string. Schema asks target_result. We should put perhaps \"C-statistic of 0.87 for UAMOCS.\" Unit \"C-statistic\". number_stated true.\n\nNeed ensure source exact quote: \"The model's C‐statistic is comparable to the 2022 ELN risk classification (0.87 vs 0.82; P = 0.162), but offers a more nuanced distinction between intermediate‐ and high‐risk groups.\" Exact uses nonbreaking hyphen C‐statistic and intermediate‐. We can reproduce. Is 0.87 unambiguously model's? \"model's C-statistic is comparable ... (0.87 vs 0.82)\" comparison ordering likely model vs ELN. Could quote preceding context: \"We developed an unsupervised multi‐omics classification system (UAMOCS) with these data. ... The model's...\" Exact contiguous quote could span all, but no need. To make attribution clearer, include \"The model's C-statistic...\" enough.\n\nUnit maybe \"C-statistic\". Let's reason schema semantics from instruction: {\"parent_value\": number, \"unit\": string, ...}. Parent_value perhaps generic numeric extraction. Unit could be \"%\", \"subjects\", etc. For C-statistic, likely unit \"\" (unitless). But they explicitly demand unit must be unit paper prints. It prints no unit for C-statistic; metric itself perhaps not unit. Should unit be empty string. Yet phrase \"unit must be the unit the paper prints\" likely if result is e.g. 0.87 then unit should be \"C-statistic\" because printed descriptor. They distinguish unit from target_result. Typical extraction asks parent_value and unit; dimensionless metrics often use metric name as unit. Need inspect likely benchmark conventions. They may expect:\n{\n \"parent_value\": 0.87,\n \"unit\": \"C-statistic\",\n \"evidence\": \"\\\"The model's C‐statistic ...\\\"\",\n \"target_result\": \"UAMOCS model C-statistic\",\n \"number_stated\": true\n}\nThis seems reasonable.\n\nBut perhaps headline numerical result is \"1391\" and unit \"subjects\". Let's assess wording. Abstract: \"We tried to increase prediction accuracy using a multi‐omics strategy. We interrogated data from 1391 consecutive, newly diagnosed subjects with AML...\" This is sample size, a major headline numerical result. Then model performance C-statistic. User asks \"find the single numerical result that a replication of the registered target has to reproduce.\" They may have a target result concept from some benchmark where target is registered by user in natural terms. Here REGISTERED TARGET itself is generic, not specific metric. Need identify paper's headline numerical result. Usually abstract result headline might be C-statistic. They explicitly caution \"Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause...\" This suggests number may be one among comparison list and need attribution. The sentence with 0.87 vs 0.82 indeed needs attribution ordering. Could be testing ambiguity. The target says \"headline numerical result the paper states for its main finding.\" We need choose one from several numerical statements. \"The model's C-statistic ... (0.87 vs 0.82; P=...)\" likely main finding metric.\n\nCould headline result be \"1391\" because that's first numerical result? But replication has to reproduce sample count perhaps, though \"main finding\" not sample size. Single headline number likely 0.87. They ask \"value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed.\" So extraction direct. If target is headline result, 0.87 is direct. If overall survival rates perhaps no actual rates, only p values. There are numerous numbers. Main performance is C-statistic. The paper title prognosis prediction value; key claim model C-statistic 0.87, compared 0.82. Yes.\n\nCould \"headline numerical result\" be 1391 subjects because cohort? Abstract first line says \"We interrogated data from 1391...\" But replication of main finding requires reproduce cohort and model performance. Yet a \"headline numerical result\" convention often selects primary metric, not sample size.\n\nNeed output exact JSON, no markdown. Evidence quote could be just exact sentence. Unit \"C-statistic\". target_result maybe \"UAMOCS model C-statistic of 0.87.\" They say headline number only perhaps target_result should perhaps only identify target, not add extra numbers? They require target_result string. Maybe \"UAMOCS model C-statistic\" avoids duplicate value and comparator. Evidence contains all quote numbers though instruction asks exact contiguous quote containing the number, and whole clause due attribution. They say \"Report the headline number only\" likely means don't report 0.82 in parent_value; evidence necessarily may contain it. Good.\n\nUse Unicode exact quote. JSON escaping apostrophe doesn't need. Could evidence include leading/trailing quotation marks? Those wouldn't be source text exactly if added; quote field itself enough. Exact content sentence.\n\nShould target_result mention 0.87? likely yes. \"UAMOCS model's C-statistic is 0.87.\" But headline number only maybe this is appropriate. Unit \"C-statistic\". Let's ensure \"paper prints\" term exactly C‐statistic with nonbreaking hyphen. Unit should perhaps preserve C‐statistic. Use that.\n\nNeed only JSON.</think>\n\n{\"parent_value\":0.87,\"unit\":\"C‐statistic\",\"evidence\":\"The model's C‐statistic is comparable to the 2022 ELN risk classification (0.87 vs 0.82; P = 0.162), but offers a more nuanced distinction between intermediate‐ and high‐risk groups.\",\"target_result\":\"The UAMOCS model's C‐statistic is 0.87.\",\"number_stated\":true}", "reading": {"parent_value": 0.87, "unit": "C‐statistic", "evidence": "The model's C‐statistic is comparable to the 2022 ELN risk classification (0.87 vs 0.82; P = 0.162), but offers a more nuanced distinction between intermediate‐ and high‐risk groups.", "target_result": "The UAMOCS model's C‐statistic is 0.87.", "number_stated": true, "source_locator": "chars 1210-1392 of source sha256 0eff4cb0fc86ed00876123c89113527f0e388d7836da336fb847769bddf79f53"}, "recorded_at": "2026-10-31T15:24:20.515591+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "UAMOCS distinguishes overall survival rates across the cohorts (TCGA P = 0.042; GSE71014 P = 0.043; ihCAMs‐AML, GSE102691 and GSE37642 all P < 0.001).", "minimax_alt": "The model's C‐statistic is comparable to the 2022 ELN risk classification (0.87 vs 0.82; P = 0.162), but offers a more nuanced distinction between intermediate‐ and high‐risk groups.", "decisive": false}, "physical_methods": {"minimax": ["Ex vivo drug screening using primary AML bone marrow samples, 100% PPC concentration inhibition assays, and drug sensitivity testing across seven concentration gradients", "Cell viability assessment by luminescence measurement using CellCounting‐Lite 2.0 and an EnVision plate reader"], "minimax_alt": ["Ex vivo drug-sensitivity testing using primary bone marrow samples from the ihCAMs‐AML cohort", "Density gradient centrifugation to obtain primary cancer cells", "In vitro amplification of AML cells in AML-specific complete culture medium", "Seeding and culture of AML cells in 384‐well opaque plates with triplicate wells for each drug", "Automated drug administration using a JANUS automated workstation", "CellCounting‐Lite 2.0 luminescent cell-viability assay with relative luminescence units measured using an EnVision plate reader"], "decisive": false}, "analysis_methods": {"minimax": ["Unsupervised multi‐omics classification system (UAMOCS) integrating mutation topography, DNA methylation, and transcriptomics", "Differential methylation analysis using the ChAMP 2.18.2 R package", "Differential expression analysis using the limma package", "Gene set enrichment analysis (GSEA) using clusterProfiler and the Hallmark pathway", "Transcriptional regulon reconstruction using RTN 2.20, mutual information analysis, Spearman rank‐order correlation, permutation analysis, bootstrapping, and two-sided GSEA"], "minimax_alt": ["Unsupervised multi‐omics classification system (UAMOCS) integrating mutation topography, DNA methylation, and transcriptomics", "C‐statistic comparison with the 2022 ELN risk classification", "Differential methylated probe analysis using the ‘ChAMP 2.18.2’ R package", "Differential expression analysis using the ‘limma’ R package", "Gene set enrichment analysis (GSEA) using a preranked gene list and the clusterProfiler R package with the Hallmark pathway", "Transcriptional regulon reconstruction using the ‘RTN 2.20’ R package, mutual information analysis, Spearman rank‐order correlation, permutation analysis, bootstrapping, and data processing inequality filtering", "Individual regulon activity estimation by two‐sided GSEA"], "decisive": false}, "statistical_method": {"minimax": "", "minimax_alt": "C‐statistic", "decisive": true}, "unit": {"minimax": "C-statistic", "minimax_alt": "C‐statistic", "decisive": true}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:1491099fb7a9c9340144749357c297e848c0f014306f3a63b674a95afc800a3e", "type": "sep_package", "label": "SEP v1 package for pmid:39927613"}], "activities": [{"id": "activity:conversion:pmid:39927613", "type": "conversion", "used": ["package:1491099fb7a9c9340144749357c297e848c0f014306f3a63b674a95afc800a3e"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:39927613", "parent_hash": "sha256:b3c99c95b33b212cd7f48ef10967aa0a6dab7f7f7f5927f2745e1f639e6b9027", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:39927613 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:39927613' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:48:45+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}